{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:05:52Z","timestamp":1730297152653,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022676","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"174-181","source":"Crossref","is-referenced-by-count":0,"title":["Guided Contrastive Self-Supervised Pre-Training for Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Aparna","family":"Khare","sequence":"first","affiliation":[{"name":"Amazon Alexa,USA"}]},{"given":"Minhua","family":"Wu","sequence":"additional","affiliation":[{"name":"Amazon Alexa,USA"}]},{"given":"Saurabhchand","family":"Bhati","sequence":"additional","affiliation":[{"name":"Amazon Alexa,USA"}]},{"given":"Jasha","family":"Droppo","sequence":"additional","affiliation":[{"name":"Amazon Alexa,USA"}]},{"given":"Roland","family":"Maas","sequence":"additional","affiliation":[{"name":"Amazon Alexa,USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4171","article-title":"Bert: Pre-training of deep bidi-rectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Devlin"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"volume-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2922832"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1473"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054458"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","article-title":"Rep-resentation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"International Conference on Learning Representations","author":"Baevski","key":"ref13"},{"key":"ref14","article-title":"wav2vec 2. 0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Ad-vances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-936"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","article-title":"Wav2letter: an end-to-end convnet-based speech recognition system","author":"Collobert","year":"2016","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"10937","article-title":"Unispeech: Unified speech representation learning with labeled and unlabeled data","volume-title":"Proceedings of the ICML","author":"Wang","year":"2021"},{"key":"ref20","article-title":"Unispeech at scale: An empirical study of pre-training method on large-scale speech recognition dataset","author":"Wang","year":"2021","journal-title":"ar Xiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414227"},{"article-title":"Hybrid un-supervised and supervised multitask learning for speech recognition in low resource languages","volume-title":"Proc. Work-shop on Machine Learning in Speech and Language Processing","author":"Raghavan","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"ref24","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proceedings of the thirteenth international conference on artificial intelli-gence and statistics. JMLR Workshop and Conference Proceedings","author":"Gutmann"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"issue":"11","key":"ref29","article-title":"Visu-alizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022676.pdf?arnumber=10022676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:34:11Z","timestamp":1707813251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022676\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022676","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}